{"id":"https://openalex.org/W4406450033","doi":"https://doi.org/10.1109/iccv51701.2025.01684","title":"FramePainter: Endowing Interactive Image Editing with Video Diffusion Priors","display_name":"FramePainter: Endowing Interactive Image Editing with Video Diffusion Priors","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4406450033","doi":"https://doi.org/10.1109/iccv51701.2025.01684"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01684","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01684","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2501.08225","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088930145","display_name":"Yabo Zhang","orcid":"https://orcid.org/0000-0002-1019-4334"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yabo Zhang","raw_affiliation_strings":["Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046023089","display_name":"Xinpeng Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinpeng Zhou","raw_affiliation_strings":["Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025046374","display_name":"Yihan Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Yihan Zeng","raw_affiliation_strings":["Huawei Noah&#x0027;s Ark Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah&#x0027;s Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100597609","display_name":"Hang Xu","orcid":"https://orcid.org/0009-0009-4669-6078"},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Hang Xu","raw_affiliation_strings":["Huawei Noah&#x0027;s Ark Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah&#x0027;s Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100634946","display_name":"Hui Li","orcid":"https://orcid.org/0000-0002-4404-8845"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Li","raw_affiliation_strings":["Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100636655","display_name":"Wangmeng Zuo","orcid":"https://orcid.org/0000-0002-3330-783X"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wangmeng Zuo","raw_affiliation_strings":["Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"18121","last_page":"18131"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9264000058174133,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9264000058174133,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9189000129699707,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6506116390228271},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.6416041851043701},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.6401950716972351},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.5848888158798218},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5421122312545776},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5412364602088928},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5303911566734314},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3986940383911133},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.34093913435935974},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.09220948815345764},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07027733325958252}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6506116390228271},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.6416041851043701},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.6401950716972351},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.5848888158798218},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5421122312545776},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5412364602088928},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5303911566734314},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3986940383911133},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.34093913435935974},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.09220948815345764},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07027733325958252},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01684","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01684","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2501.08225","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.08225","pdf_url":"https://arxiv.org/pdf/2501.08225","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2501.08225","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2501.08225","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2501.08225","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.08225","pdf_url":"https://arxiv.org/pdf/2501.08225","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G870499228","display_name":null,"funder_award_id":"2023YFA1008500","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4319453795","https://openalex.org/W4205104112","https://openalex.org/W4406058807","https://openalex.org/W1974870326","https://openalex.org/W2770776392","https://openalex.org/W3176454756","https://openalex.org/W2772330423","https://openalex.org/W3163523050","https://openalex.org/W3006381446","https://openalex.org/W3015353979"],"abstract_inverted_index":{"Interactive":[0],"image":[1,151],"editing":[2,118,164,182],"allows":[3],"users":[4],"to":[5,58,84,116,138],"modify":[6],"images":[7],"through":[8],"visual":[9,63],"interaction":[10],"operations":[11],"such":[12,21],"as":[13,26,72,96],"drawing,":[14],"clicking,":[15],"and":[16,52,62,88,149,157,180],"dragging.":[17],"Existing":[18],"methods":[19,171],"construct":[20],"supervision":[22],"signals":[23],"from":[24],"videos,":[25,205],"they":[27],"capture":[28],"how":[29],"objects":[30],"change":[31],"with":[32,104,172],"various":[33,162],"physical":[34],"interactions.":[35],"However,":[36],"these":[37],"models":[38],"are":[39],"usually":[40],"built":[41],"upon":[42],"text-to-image":[43],"diffusion":[44,82],"models,":[45],"so":[46,77],"necessitate":[47],"(i)":[48],"massive":[49],"training":[50,86,175],"samples":[51],"(ii)":[53],"an":[54,73,97],"additional":[55],"reference":[56],"encoder":[57,115],"learn":[59],"real-world":[60,204],"dynamics":[61],"consistency.":[64,91],"In":[65],"this":[66,70,101],"paper,":[67],"we":[68,93,133],"reformulate":[69],"task":[71],"image-to-video":[74],"generation":[75],"problem,":[76],"that":[78],"inherit":[79],"powerful":[80],"video":[81],"priors":[83],"reduce":[85],"costs":[87],"ensure":[89],"temporal":[90,124],"Specifically,":[92],"introduce":[94],"FramePainter":[95,160,194],"efficient":[98],"instantiation":[99],"of":[100,123,159,163,183,190],"formulation.":[102],"Initialized":[103],"Stable":[105],"Video":[106],"Diffusion,":[107],"it":[108,166],"only":[109],"uses":[110],"a":[111],"lightweight":[112],"sparse":[113],"control":[114],"inject":[117],"signals.":[119],"Considering":[120],"the":[121,140,155,188,191,208],"limitations":[122],"attention":[125,137],"in":[126,199,203],"handling":[127],"large":[128],"motion":[129],"between":[130,147],"two":[131],"frames,":[132],"further":[134],"propose":[135],"matching":[136],"enlarge":[139],"receptive":[141],"field":[142],"while":[143],"encouraging":[144],"dense":[145],"correspondence":[146],"edited":[148],"source":[150],"tokens.":[152],"We":[153],"highlight":[154],"effectiveness":[156],"efficiency":[158],"across":[161],"signals:":[165],"domainantly":[167],"outperforms":[168],"previous":[169],"state-of-the-art":[170],"far":[173],"less":[174],"data,":[176],"achieving":[177],"highly":[178],"seamless":[179],"coherent":[181],"images,":[184],"\\eg,":[185,206],"automatically":[186],"adjust":[187],"reflection":[189],"cup.":[192],"Moreover,":[193],"also":[195],"exhibits":[196],"exceptional":[197],"generalization":[198],"scenarios":[200],"not":[201],"present":[202],"transform":[207],"clownfish":[209],"into":[210],"shark-like":[211],"shape.":[212],"Our":[213],"code":[214],"will":[215],"be":[216],"available":[217],"at":[218],"https://github.com/YBYBZhang/FramePainter.":[219]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
